© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 141
    Prev
    Next
    INDEX
    Explanations

    baseball player names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¥Ķé©°
    -0.25
     Realty
    -0.24
    夷
    -0.23
    èĴ½
    -0.23
    PictureBox
    -0.23
    æ²¹èĦĤ
    -0.23
     upscale
    -0.23
    迷失
    -0.23
    æĺ¥é£İ
    -0.23
    phen
    -0.23
    POSITIVE LOGITS
     splice
    0.25
     CPL
    0.25
     cable
    0.24
    帷
    0.24
     кап
    0.24
    çļĩåIJİ
    0.24
     pasta
    0.23
     reflex
    0.23
     nod
    0.23
    cripts
    0.23
    Activations Density 0.016%

    No Known Activations